© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 4225
    Prev
    Next
    INDEX
    Explanations

    skin, mutation, change, instructions, dry, .` , Roles, random

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quedaría
    0.43
     সত্যি
    0.41
     trazer
    0.40
    ᱖
    0.39
    将会
    0.39
     eventualmente
    0.38
     đem
    0.38
     iria
    0.38
     nozzle
    0.38
     поможет
    0.38
    POSITIVE LOGITS
     referred
    0.39
    ana
    0.38
    referred
    0.37
     from
    0.36
     conferred
    0.36
     en
    0.35
    anch
    0.35
     =
    0.34
    est
    0.34
     pulled
    0.34
    Activations Density 0.087%

    No Known Activations